Scientific Programme Monday, 09 September 2019 [BC]2 Session , University of Basel Seminarraum 106 09:00 - 16:00 T1: Using the Ensembl REST APIs to programmatically access genomic data Room Seminarraum 106 Overview The Ensembl project provides a comprehensive and integrated source of annotation of genome sequences, including genes, genetic variation, features that regulate gene expression, homologues and alignments. These data are accessible programmatically in a language agnostic manner via the Ensembl REST APIs. Scripting against public databases like Ensembl facilitates quick retrieval of valuable data in your preferred format or can be integrated into pipelines for data analysis. This tutorial is aimed at researchers and developers interested in exploring Ensembl beyond the website. The workshop covers how to use the Ensembl REST APIs, including understanding the major endpoints and how to write scripts to call them. Feedback from previous courses •“Wish I had taken the course long time ago. Didn’t know before how good and powerful APIs are!” API workshop, EMBL-EBI, January 2016 •“I really enjoyed the course, and the ENSEMBL API will become a very relevant part of my toolset.” API workshop, Cambridge, December 2013 Audience and requirements The tutorial is aimed at bioinformatics and wet-lab researchers who use genomic data and would like to use scripting to access these data directly, including integrating into pipelines. This is a hands-on training course and participants will need to bring a laptop with WiFi enabled in order to take part. Participants must be able to code in Python, Perl or R. The training will utilise Jupyter Notebooks hosted by Microsoft Azure – to use these all participants will need to have a free Microsoft Account. Maximum participants: 20 Organiser: Astrid Gall (Ensembl Outreach Team, EMBL-EBI, United Kingdom) 09:00 - 09:45 Introduction to ensembl and its data types 09:45 - 10:30 Overview of the ensembl REST API 10:30 - 11:00 Tea/Coffee Break 11:00 - 11:45 Accessing GET queries with the ensembl REST API 11:45 - 12:30 Decoding json; other content types 12:30 - 13:30 Lunch 13:30 - 14:30 Chaining REST queries together 14:30 - 15:30 Accessing POST queries with the ensembl REST API 15:30 - 16:00 Rate-limiting Page 1 / 67 Scientific Programme [BC]2 Session , University of Basel Seminarraum 107 09:00 - 16:00 T2: Genomic epidemiology and phylodynamics with Nextstrain Room Seminarrraum 107 Overview Mutations that accumulate in pathogen genome sequences contain information on the pathogen's evolutionary history and allow us to reconstruct patterns of transmission. Since sequencing capacity and surveillance has increased by orders of magnitude in recent years, data sharing, timely analysis, and dissemination of results has become crucial for harnessing the power of genomics in public health. Nextstrain is an open-source project for phylodynamic analysis, data integration, and visualization of large data sets of viral and bacterial pathogens. Nextstrain can analyse thousands of sequences within minutes and visualizes the results using an interactive browser- based interface (see Fig. 1). This interface can be used locally on the user's computer or shared on the internet. Audience and requirements The workshop is targeted to users with basic bioinformatic knowledge that want to use the Nextstrain pipeline to analyse and visualize their own data. The workshop would be split into a morning session covering background, the structure and use of Nextstrain tools, and tutorials using example data, and an afternoon session where users analyse their own data. Participants would be expected to bring their own laptops. Nextstrain is extensively tested on Linux, MacOS, and Windows 10 with Linux Subsystem and can be installed via conda and npm. Maximum participants: 23 Organiser: Emma Hodcroft (Biozentrum University of Basel & SIB Swiss Institute of Bioinformatics, Basel, Switzerland) Organiser: Richard Neher (Biozentrum University of Basel & SIB Swiss Institute of Bioinformatics, Basel, Switzerland) 09:00 - 10:00 Basics of genomic epidemiology and phylogenetics 10:00 - 11:00 The Nextstrain interface and interactive visualization 11:00 - 12:00 From input to output: analysis pipelines using snakemake and augur 12:00 - 13:00 Conducting phylodynamic analysis using treetime 13:00 - 14:00 Interactive, step-by-step tutorials for viral and bacterial pathogens 14:00 - 15:00 Cleaning and formatting your data 15:00 - 15:30 Assembling a data-set specific snakefile 15:30 - 16:00 Visualization locally and online Page 2 / 67 Scientific Programme [BC]2 Session , University of Basel Regenzimmer 111 09:00 - 16:30 T3: Introduction to machine learning: opportunities for advancing omics data analysis Room Regenzzimmer 111 Overview Machine learning has emerged as a discipline that enables computers to assist humans in making sense of large and complex data sets. With the drop-in cost of sequencing technologies, large amounts of omics data are being generated and made accessible to researchers. Analysing these complex high-volume data is not trivial and the use of classical tools cannot explore their full potential. Machine learning can thus be very useful in mining large omics datasets to uncover new insights that can advance the field of medicine and improve health care. The aim of this tutorial is to introduce participants to the Machine learning (ML) taxonomy and common machine learning algorithms. The tutorial will cover the methods being used to analyse different omics data sets by providing a practical context through the use of basic but widely used R and Python libraries. The tutorial will comprise a number of hands on exercises and challenges, where the participants will acquire a first understanding of the standard ML processes as well as the practical skills in applying them on familiar problems and publicly available real-world data sets. Learning objectives •Understand the ML taxonomy and the commonly used machine learning algorithms for analysing “omics” data •Understand differences between ML algorithms categories and to which kind of problem they can be applied •Understand different applications of ML in different -omics studies •Use some basic, widely used Python and R packages for ML •Interpret and visualize the results obtained from ML analyses on omics datasets •Apply the ML techniques to analyse their own datasets Audience and requirements This introductory tutorial is aimed towards bioinformaticians (graduate students and researchers) familiar with different omics data technologies that are interested in applying machine learning to analyse them. Prerequisites •Previous experience in Bioinformatics analysis •Familiarity with any programming language (especially R) is preferable but not necessary Maximum participants: 30 Organiser: Amel Ghouila (Institut Pasteur de Tunis, H3ABioNet, Tunisia) Organiser: Fotis Psomopoulos (INAB|CERTH ELIXIR-GR, Certh, Greece) 09:00 - 09:15 Tutorial introduction, get to know each other and, setup Part I: Background 09:15 - 10:45 Introduction to ML / DM: Data mining / machine learning basic concepts / taxonomy of ML and examples of algorithms / deep learning overview 10:45 - 11:00 break 11:00 - 12:30 Applications of ML in bioinformatics: examples of different ML/DM techniques that can be applied to different NGS data analysis pipelines / how to choose the right ML technique 12:30 - 13:15 break 13:15 - 14:45 Loading and exploring omics data: what is exploratory data analysis (EDA) and why is it useful? Unsupervised learning how could unsupervised learning be used to analyze omics data? Part II: Hands-on 14:45 - 15:00 break Page 3 / 67 Scientific Programme 15:00 - 16:30 Supervised learning I: classification how could supervised learning be used to analyze omics data? Supervised learning II: regression what if the target variable is numerical rather than categorical? Closing, discussion and resource sharing [BC]2 Session , University of Basel Hörsaal 117 09:00 - 16:00 T4: Interpretability for deep learning models in computational biology Room Hörsaal 117 Overview The recent application of deep neural networks to long-standing problems such as the prediction of functional DNA sequences, the inference of protein-protein interactions or the detection of cancer cells in histopathology images has brought a break-through in performance and prediction power. However, high accuracy often comes at the price of loss of interpretability, i.e. many of these models are built as black-boxes that fail to provide new biological insights. This tutorial focuses on illustrating some of the recent advancements in the field of Interpretable Artificial Intelligence. We will show how explainable, smaller models can achieve similar levels of performance than cumbersome ones, while shedding light on the underlying biological principles driving model decisions. We will demonstrate how to build and extract knowledge using interpretable approaches in two different domains of computational biology, (1) the functional analysis of raw DNA sequencing data and (2) drug sensitivity prediction models. The choice of these two applications is motivated by the availability of adequately large datasets that can support deep learning (DL) approaches and by their high relevance for personalized medicine. We will exploit both publicly available deep learning models as well as in-house developed models. Learning objectives The tutorial is aimed to strike the right balance between theoretical input and practical exercises. The tutorial
Details
-
File Typepdf
-
Upload Time-
-
Content LanguagesEnglish
-
Upload UserAnonymous/Not logged-in
-
File Pages67 Page
-
File Size-